Inference for a family of survival models encompassing the proportional hazards and proportional odds models

2005 ◽  
Vol 25 (6) ◽  
pp. 995-1014 ◽  
Author(s):  
David M. Zucker ◽  
Song Yang
Keyword(s):  
Proportional Hazards ◽  
Survival Models ◽  
Proportional Odds ◽  
Proportional Odds Models

Tests of Proportional Hazards and Proportional Odds Models for Grouped Survival Data

Biometrics ◽  
2000 ◽  
Vol 56 (4) ◽  
pp. 1233-1240 ◽  
Author(s):  
Enrico A. Colosimo ◽  
Liciana V. A. S. Chalita ◽  
Clarice G. B. Demétrio
Keyword(s):  
Survival Data ◽  
Proportional Hazards ◽  
Proportional Odds ◽  
Proportional Odds Models

Parametric and penalized generalized survival models

2016 ◽  
Vol 27 (5) ◽  
pp. 1531-1546 ◽  
Author(s):  
Xing-Rong Liu ◽  
Yudi Pawitan ◽  
Mark Clements
Keyword(s):  
Proportional Hazards ◽  
Proportional Hazards Model ◽  
Information Criteria ◽  
Parametric Models ◽  
Survival Models ◽  
Link Function ◽  
Proportional Odds ◽  
Linear Predictor ◽  
Time Effects ◽  
Covariate Effects

We describe generalized survival models, where g( S( t| z)), for link function g, survival S, time t, and covariates z, is modeled by a linear predictor in terms of covariate effects and smooth time effects. These models include proportional hazards and proportional odds models, and extend the parametric Royston–Parmar models. Estimation is described for both fully parametric linear predictors and combinations of penalized smoothers and parametric effects. The penalized smoothing parameters can be selected automatically using several information criteria. The link function may be selected based on prior assumptions or using an information criterion. We have implemented the models in R. All of the penalized smoothers from the mgcv package are available for smooth time effects and smooth covariate effects. The generalized survival models perform well in a simulation study, compared with some existing models. The estimation of smooth covariate effects and smooth time-dependent hazard or odds ratios is simplified, compared with many non-parametric models. Applying these models to three cancer survival datasets, we find that the proportional odds model is better than the proportional hazards model for two of the datasets.

scholarly journals Are children more vulnerable to mesothelioma than adults? A comparison of mesothelioma risk among children and adults exposed non-occupationally to blue asbestos at Wittenoom

2018 ◽  
Vol 75 (12) ◽  
pp. 898-903 ◽  
Author(s):  
Alison Reid ◽  
Peter Franklin ◽  
Geoffrey Berry ◽  
Susan Peters ◽  
Nita Sodhi-Berry ◽  
...  
Keyword(s):  
Proportional Hazards ◽  
Asbestos Exposure ◽  
Age Groups ◽  
Developed Countries ◽  
Incidence Rates ◽  
Cumulative Exposure ◽  
Survival Models ◽  
Response Relationship ◽  
Exposure Response ◽  
Long Latency

ObjectivesThe presence of asbestos in public buildings is a legacy of past asbestos use in many developed countries. Of particular concern is the amount and current condition in schools and the vulnerability of children to mesothelioma. Our aim was to compare the risk of mesothelioma between those exposed to blue asbestos as children and as adults at Wittenoom.MethodsPublic sources were used to establish the Wittenoom residents’ cohort. Mesothelioma incidence rates per 100 000 person-years at risk were derived for those first exposed to asbestos at Wittenoom as children (<15 years) or adults separately. Proportional hazards survival models examined the slope of the exposure-response relationship between asbestos exposure and incidence of mesothelioma in different sex and age groups.ResultsThe mesothelioma rate was lower among those first exposed as children (76.8 per 100 000) than those first exposed as adults (121.3 per 100 000). Adjusting for cumulative exposure to asbestos and sex, those exposed as adults had a greater risk of mesothelioma (adjusted HR 2.5, 95% CI 1.7 to 3.7). The slope of the exposure-response relationship did not differ between those exposed as children and those exposed as adults.ConclusionWe found no greater susceptibility to mesothelioma among those first exposed to asbestos as children than those first exposed as adults. However, given the long latency of mesothelioma, and the greater years of life yet to be lived by the Wittenoom children, it is likely that there will be more cases of mesothelioma in the future among those first exposed as children.

scholarly journals C-mix: A high-dimensional mixture model for censored durations, with applications to genetic data

2018 ◽  
Vol 28 (5) ◽  
pp. 1523-1539
Author(s):  
Simon Bussy ◽  
Agathe Guilloux ◽  
Stéphane Gaïffas ◽  
Anne-Sophie Jannot
Keyword(s):  
Mixture Model ◽  
Proportional Hazards ◽  
Expectation Maximization Algorithm ◽  
Cox Proportional Hazards ◽  
Elastic Net ◽  
Survival Models ◽  
High Dimensional ◽  
Survival Prediction ◽  
Monte Carlo Simulation Study ◽  
Cox Proportional Hazards Models

We introduce a supervised learning mixture model for censored durations (C-mix) to simultaneously detect subgroups of patients with different prognosis and order them based on their risk. Our method is applicable in a high-dimensional setting, i.e. with a large number of biomedical covariates. Indeed, we penalize the negative log-likelihood by the Elastic-Net, which leads to a sparse parameterization of the model and automatically pinpoints the relevant covariates for the survival prediction. Inference is achieved using an efficient Quasi-Newton Expectation Maximization algorithm, for which we provide convergence properties. The statistical performance of the method is examined on an extensive Monte Carlo simulation study and finally illustrated on three publicly available genetic cancer datasets with high-dimensional covariates. We show that our approach outperforms the state-of-the-art survival models in this context, namely both the CURE and Cox proportional hazards models penalized by the Elastic-Net, in terms of C-index, AUC( t) and survival prediction. Thus, we propose a powerful tool for personalized medicine in cancerology.

Network meta-analysis (NMA) of pembrolizumab for first-line (1L) treatment of recurrent/metastatic (R/M) head and neck squamous cell carcinoma (HNSCC).

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e18012-e18012
Author(s):  
Karthik Ramakrishnan ◽  
Ali Mojebi ◽  
Dieter Ayers ◽  
Diana Romana Chirovsky ◽  
Rebekah Borse ◽  
...  
Keyword(s):  
Sensitivity Analysis ◽  
Fixed Effects ◽  
Goodness Of Fit ◽  
Proportional Hazards ◽  
Treatment Options ◽  
Deviance Information Criterion ◽  
Progression Free Survival ◽  
Survival Models ◽  
Base Case ◽  
Eligibility Criteria

e18012 Background: In the KEYNOTE-048 trial, pembrolizumab as monotherapy (P) and in combination with platinum+5FU chemotherapy (P+C) versus cetuximab+platinum+5FU (EXTREME regimen) significantly improved overall survival (OS) in the combined positive score (CPS) ≥1 (hazard ratio: 0.74; 95% confidence interval: 0.61-0.90) and total (0.72; 0.60-0.87) R/M HNSCC populations, respectively, and was approved by the FDA in these patient populations. While the EXTREME regimen is considered standard of care in 1L R/M HNSCC, other systemic treatment options including cetuximab+platinum+docetaxel (TPEx regimen), platinum+paclitaxel/taxane (Pt+T), and platinum+5FU (Pt+F) are also commonly used. Due to lack of head-to-head comparisons with pembrolizumab, an NMA was conducted to estimate the comparative efficacy of P and P+C versus these interventions in 1L R/M HNSCC. Methods: A systematic literature review (SLR) was conducted on November 13, 2019 to identify randomized controlled trials for the relavant interventions. Data were extracted for the OS and progression-free survival (PFS) outcomes. NMA analyses were conducted for the total population and for the CPS ≥1 and CPS ≥20 subgroups in a Bayesian framework using proportional hazards (base case) and time-varying (sensitivity analysis) treatment-effect models. The deviance information criterion was used to compare the goodness-of-fit of the alternative survival models. Results: The SLR identified 28 trials, of which six trials matched the trial eligibility criteria of KEYNOTE-048 and were included in the NMA. Results from the fixed-effects NMA for P and P+C are summarized in table below for the FDA indicated population. Improvement in OS was noted for P and P+C versus EXTREME, Pt+T, and Pt+F, and a trend in improved OS versus TPEx was observed. The sensitivity analysis showed improved OS over time across all comparisons. PFS was improved with P and P+C versus Pt+F and comparable versus other interventions. These results were generally consistent for P and P+C in the CPS (CPS ≥1 or CPS ≥20) patient subgroups. Additionally, NMA results versus EXTREME were consistent with the KEYNOTE-048 trial results. Conclusions: Pembrolizumab (P or P+C), showed improved OS and comparable PFS outcomes versus alternative 1L R/M HNSCC interventions, consistent with the efficacy results versus EXTREME observed in the KEYNOTE-048 trial. [Table: see text]

A Two-stage Multilevel Randomized Response Technique With Proportional Odds Models and Missing Covariates

2020 ◽  
pp. 004912412091495
Author(s):  
Shu-Hui Hsieh ◽  
Shen-Ming Lee ◽  
Chin-Shang Li
Keyword(s):  
Missing At Random ◽  
Missing Covariates ◽  
Randomized Response ◽  
Personal Privacy ◽  
Proportional Odds ◽  
Two Stage ◽  
Inverse Probability ◽  
Wide Range ◽  
Proportional Odds Models ◽  
Income Data

Surveys of income are complicated by the sensitive nature of the topic. The problem researchers face is how to encourage participants to respond and to provide truthful responses in surveys. To correct biases induced by nonresponse or underreporting, we propose a two-stage multilevel randomized response (MRR) technique to investigate the true level of income and to protect personal privacy. For a wide range of applications, we present a proportional odds model for two-stage MRR data and apply inverse probability weighting and multiple imputation methods to deal with covariates on some subjects that are missing at random. A simulation study is conducted to investigate the effects of missing covariates and to evaluate the performance of the proposed methods. The practicality of the proposed methods is illustrated with the regular monthly income data collected in the Taiwan Social Change Survey. Furthermore, we provide an estimate of personal regular monthly mean income.

Multimorbidity and Polypharmacy Are Independently Associated With Mortality in Older People With Intellectual Disabilities: A 5-Year Follow-Up From the HA-ID Study

2018 ◽  
Vol 123 (1) ◽  
pp. 72-82 ◽  
Author(s):  
Josje D. Schoufour ◽  
Alyt Oppewal ◽  
Hanne J.K. van der Maarl ◽  
Heidi Hermans ◽  
Heleen M. Evenhuis ◽  
...  
Keyword(s):  
Down Syndrome ◽  
Older People ◽  
Proportional Hazards ◽  
Cox Proportional Hazards ◽  
Survival Models ◽  
Future Research ◽  
Mortality Data ◽  
Chronic Medication ◽  
Wide Range

Abstract We studied the association between multimorbidity, polypharmacy, and mortality in 1,050 older adults (50+) with intellectual disability (ID). Multimorbidity (presence of ≥ 4 chronic health conditions) and polypharmacy (presence ≥ 5 chronic medication prescriptions) were collected at baseline. Multimorbidity included a wide range of disorders, including hearing impairment, thyroid dysfunction, autism, and cancer. Mortality data were collected during a 5-year follow-up period. Cox proportional hazards models were used to determine the independent association between multimorbidity and polypharmacy with survival. Models were adjusted for age, sex, level of ID, and the presence of Down syndrome. We observed that people classified as having multimorbidity or polypharmacy at baseline were 2.60 (95% CI = 1.86–3.66) and 2.32 (95% CI = 1.70–3.16) times more likely to decease during the follow-up period, respectively, independent of age, sex, level of ID, and the presence of Down syndrome. Although slightly attenuated, we found similar hazard ratios if the model for multimorbidity was adjusted for polypharmacy and vice versa. We showed for the first time that multimorbidity and polypharmacy are strong predictors for mortality in people with ID. Awareness and screening of these conditions is important to start existing treatments as soon as possible. Future research is required to develop interventions for older people with ID, aiming to reduce the incidence of polypharmacy and multimorbidity.

Sign in / Sign up

Export Citation Format

Share Document